Triple

T20744377
Position Surface form Disambiguated ID Type / Status
Subject John Duttine E510536 entity
Predicate notableWork P4 FINISHED
Object People Like Us — NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: People Like Us | Statement: [John Duttine, notableWork, People Like Us]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: People Like Us
Context triple: [John Duttine, notableWork, People Like Us]
  • A. People Like Us
    People Like Us is a 2012 American drama film about a man who discovers he has a previously unknown half-sister after his father's death.
  • B. People Like Us
    People Like Us is a musical act connected to the British rock band Supertramp, likely involving collaborations or shared members.
  • C. People Like Us
    "People Like Us" is the final studio album by American folk rock group The Mamas & the Papas, released in 1971 after the band had effectively disbanded.
  • D. People Like Us chosen
    People Like Us is a stage play written by British actor and playwright Frank Vosper.
  • E. Millions Like Us
    Millions Like Us is a 1943 British World War II drama film depicting the lives and relationships of women working in a wartime factory on the home front.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0b4c845e88190b4c5f3ae79291182 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c21197088190951a4c4a7e765891 completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:33 p.m.